_ Git - youtube-dl/blob - youtube_dl/extractor/aol.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9 )
  10
  11
  12 class AolIE(InfoExtractor):
  13     IE_NAME = 'on.aol.com'
  14     _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/video/.*-)(?P<id>[^/?-]+)'
  15
  16     _TESTS = [{
  17         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
  18         'md5': '18ef68f48740e86ae94b98da815eec42',
  19         'info_dict': {
  20             'id': '518167793',
  21             'ext': 'mp4',
  22             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  23             'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
  24             'timestamp': 1395405060,
  25             'upload_date': '20140321',
  26             'uploader': 'Newsy Studio',
  27         },
  28         'params': {
  29             # m3u8 download
  30             'skip_download': True,
  31         }
  32     }, {
  33         'url': 'http://on.aol.com/video/netflix-is-raising-rates-5707d6b8e4b090497b04f706?context=PC:homepage:PL1944:1460189336183',
  34         'info_dict': {
  35             'id': '5707d6b8e4b090497b04f706',
  36             'ext': 'mp4',
  37             'title': 'Netflix is Raising Rates',
  38             'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
  39             'upload_date': '20160408',
  40             'timestamp': 1460123280,
  41             'uploader': 'Veuer',
  42         },
  43         'params': {
  44             # m3u8 download
  45             'skip_download': True,
  46         }
  47     }]
  48
  49     def _real_extract(self, url):
  50         video_id = self._match_id(url)
  51
  52         response = self._download_json(
  53             'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
  54             video_id)['response']
  55         if response['statusText'] != 'Ok':
  56             raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
  57
  58         video_data = response['data']
  59         formats = []
  60         m3u8_url = video_data.get('videoMasterPlaylist')
  61         if m3u8_url:
  62             formats.extend(self._extract_m3u8_formats(
  63                 m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  64         for rendition in video_data.get('renditions', []):
  65             video_url = rendition.get('url')
  66             if not video_url:
  67                 continue
  68             ext = rendition.get('format')
  69             if ext == 'm3u8':
  70                 formats.extend(self._extract_m3u8_formats(
  71                     video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  72             else:
  73                 f = {
  74                     'url': video_url,
  75                     'format_id': rendition.get('quality'),
  76                 }
  77                 mobj = re.search(r'(\d+)x(\d+)', video_url)
  78                 if mobj:
  79                     f.update({
  80                         'width': int(mobj.group(1)),
  81                         'height': int(mobj.group(2)),
  82                     })
  83                 formats.append(f)
  84         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
  85
  86         return {
  87             'id': video_id,
  88             'title': video_data['title'],
  89             'duration': int_or_none(video_data.get('duration')),
  90             'timestamp': int_or_none(video_data.get('publishDate')),
  91             'view_count': int_or_none(video_data.get('views')),
  92             'description': video_data.get('description'),
  93             'uploader': video_data.get('videoOwner'),
  94             'formats': formats,
  95         }
  96
  97
  98 class AolFeaturesIE(InfoExtractor):
  99     IE_NAME = 'features.aol.com'
 100     _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
 101
 102     _TESTS = [{
 103         'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
 104         'md5': '7db483bb0c09c85e241f84a34238cc75',
 105         'info_dict': {
 106             'id': '519507715',
 107             'ext': 'mp4',
 108             'title': 'What To Watch - February 17, 2016',
 109         },
 110         'add_ie': ['FiveMin'],
 111     }]
 112
 113     def _real_extract(self, url):
 114         display_id = self._match_id(url)
 115         webpage = self._download_webpage(url, display_id)
 116         return self.url_result(self._search_regex(
 117             r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
 118             webpage, '5min embed url'), 'FiveMin')